Three notebooks for adding GPU acceleration to an existing Presto warehouse are now available in the Presto Prestorials Github repository. NVIDIA GPUs accelerate Presto without reinstallation or moving data. Clone and run these notebooks to setup a “hello, world” dual Presto cluster running CPU and GPU in parallel: https://github.com/prestodb/prestorials/tree/main/docker-compose-native/cpu-and-gpu The following container images are used…
What is Velox? Imagine a world where every car manufacturer had to build a completely new engine from scratch for every type of vehicle they produced, one engine specifically designed for a nimble sports car, another for a heavy-duty pickup truck, and a completely different one for a family SUV. Historically, this is exactly how…
Summary: Presto’s OpenLineage integration now captures not only where output columns come from, but how upstream columns influence them through projections, aggregations, joins, filters, grouping, sorting, windows, and conditional expressions. Note: The OpenLineage event listener was released in Presto 0.297. The richer direct and indirect column-lineage changes described in this post are merged into master,…
TL;DR — GPUs can run analytical SQL dramatically faster than CPUs: published numbers show a single node Presto C++ with GPU-accelerated operators running a TPC-H-style benchmark in ~100 seconds versus ~1,200 seconds on a high-end CPU — on the order of 12× faster — and a UCX/NVLink exchange running >6× faster with multi-node Presto. Together…
As artificial intelligence and machine learning (ML) models become integral to modern software, organizations are storing billions of high-dimensional vectors (embeddings) alongside traditional metadata. Analyzing this multi-modal data at scale requires a bridge between high-performance vector databases and distributed SQL query engines. Recently, the Presto open-source community introduced a native Lance Connector (added in release…
Introduction: The Federation Challenge in Modern Query Engines The evolution of distributed query engines has created a fundamental architectural tension. Over the past decade, the Presto ecosystem has developed an extensive collection of production-grade Java-based connectors, providing federated access to hundreds of heterogeneous data sources. Concurrently, native C++ execution engines built on frameworks like Velox…
This is a guest post from Apoorv, AI Lead Engineer at Sylus The Distributed Intelligence Challenge Problem Statement: “Show me last quarter’s ad spend next to the revenue it drove, by campaign.” While this seems like a routine request for a human analyst, it creates a significant technical hurdle for AI systems when the required…
TL;DR: What You Will Build In this comprehensive guide, you will deploy a Presto benchmarking setup using Docker Compose. We will construct a cloud-native Data Lakehouse by mapping raw data into Apache Iceberg tables stored on Google Cloud Storage (GCS). Finally, we will execute the industry-standard TPC-H and TPC-DS benchmark suites using PBench, and visualize our query latencies in real-time using a persistent MySQL and Grafana observability stack. Whether you are stress-testing…
Authentication and authorization are two main pillars for data security. While a Presto cluster can be set up to run without authentication for development purposes, production clusters must be secured at all times. Setting up secure clusters comes with its own challenges in terms of the involved setup and configuration changes. In this blog, we…
Modern data lakehouses increasingly require versioned data access, auditability, and safe experimentation without affecting production systems. Apache Iceberg allows you to maintain multiple concurrent timelines of a table through Branches and capture static historical points using Tags. This mechanism is heavily inspired by Git but operates on underlying table snapshots. In this blog, we are going to see…
Deploying Presto on Kubernetes transforms this powerful engine into a cloud-native, resilient service that automatically handles failures, scales seamlessly, and optimizes resource utilization. When combined with Helm charts, the deployment becomes standardized, version-controlled, and easily reproducible across environments. This comprehensive guide will walk you through deploying a production-capable baseline Presto cluster on Kubernetes using the official Presto Helm…
Benchmarking a distributed SQL engine like Presto involves much more than running a few queries and recording wall-clock times. Real-world performance evaluation demands multi-phase test execution, concurrent workloads, production traffic replay, and deep offline analysis. PBench is a purpose-built benchmarking toolkit for Presto that handles all of this through a declarative, composable stage system. With the 1.2.1…
In the world of big data, performance is the ultimate currency. But when you are processing petabytes of data across a distributed cluster, speed isn’t just about a stopwatch, it’s a high-stakes engineering challenge. Whether you are evaluating Presto, Spark or any other engine, you need an objective yardstick. Performance in a distributed SQL engine…
TL;DR This blog outlines the known differences between Presto and Prestissimo where existing Presto queries require adjustment to work in Prestissimo. Details Prestissimo is generally available to use and has feature parity (except for a few functions) with Presto Java. There are differences in libraries used in both stacks. Also we have ensured that bugs…
PrestoDB is a powerful distributed SQL query engine used widely for large-scale data analytics. Contributing to Presto is an excellent way to gain hands-on experience with distributed systems, Java, SQL engines, and large open-source codebases. This step-by-step tutorial is designed specifically for beginners and first-time contributors who want to build Presto from source, run the…
Presto UI is a modern, React-based web interface that provides real-time monitoring, query management, and cluster administration capabilities for the Presto distributed SQL query engine. Whether you’re a database administrator, data engineer, or developer, Presto UI offers intuitive tools to visualize query execution, monitor cluster health, and interact with the Presto coordinator. Key Benefits of…
In today’s data-driven landscape, organization’s are constantly seeking ways to analyze massive datasets quickly and efficiently. PrestoDB, a powerful open-source SQL query engine, and SingleStore, a distributed SQL database, are two technologies that, when combined, offer unparalleled capabilities for high-performance data querying and distributed analytics. This guide provides a hands-on, step-by-step tutorial on how to…
We’re excited to announce that the core Presto engine is migrating to Java 17. This upgrade reinforces our commitment to providing a robust, high-performance, and secure SQL query engine. This change allows Presto to leverage Java 17’s improvements, bringing enhancements in performance, stability, and security, and laying a strong foundation for future upgrades. Why Java…
16.5K GitHub Stars